让非技术人员用自然语言直接查询企业数据库，自动转成安全的SQL并返回可读结果。
THOR: Transformer Heuristics for On-Demand Retrieval
- 分层代理架构：问题路由、动态表结构注入、SQL生成与只读保护
- 支持最多5次LLM重试，自动修复空结果或执行错误
- 适合需要零代码访问数据的业务人员，尤其金融、销售等场景
我们提出THOR（Transformer Heuristics for On-Demand Retrieval）模块，由eSapiens安全可扩展引擎实现，将自然语言问题转化为经验证的只读SQL分析查询，用于企业数据库。Text-to-SQL模块采用解耦式编排/执行架构：监督代理负责路由，模式检索动态注入表与列元数据，SQL生成代理输出单条SELECT语句，并受只读防护机制保护。集成自校正与评分循环可捕获空结果、执行错误或低质量输出，并触发最多五次大模型驱动的重生成。最终，结果解析代理生成简洁易懂的洞察，原始数据行则交付给智能洞察引擎用于可视化或预测。在财务、销售和运营场景的烟雾测试表明，系统具备可靠的即兴查询能力与自动化周期报告功能。通过嵌入模式感知、容错执行和合规防护机制，THOR模块使非技术用户以零SQL方式访问实时数据，兼具简单性与企业级安全性。
原文摘要 · Abstract (English)
We introduce the THOR (Transformer Heuristics for On-Demand Retrieval) Module, designed and implemented by eSapiens, a secure, scalable engine that transforms natural-language questions into verified, read-only SQL analytics for enterprise databases. The Text-to-SQL module follows a decoupled orchestration/execution architecture: a Supervisor Agent routes queries, Schema Retrieval dynamically injects table and column metadata, and a SQL Generation Agent emits single-statement SELECT queries protected by a read-only guardrail. An integrated Self-Correction & Rating loop captures empty results, execution errors, or low-quality outputs and triggers up to five LLM-driven regeneration attempts. Finally, a Result Interpretation Agent produces concise, human-readable insights and hands raw rows to the Insight & Intelligence engine for visualization or forecasting. Smoke tests across finance, sales, and operations scenarios demonstrate reliable ad-hoc querying and automated periodic reporting. By embedding schema awareness, fault-tolerant execution, and compliance guardrails, the THOR Module empowers non-technical users to access live data with zero-SQL simplicity and enterprise-grade safety.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。